Kemal Yaylali
11fb6b3d73
An end-to-end audit found the repo could not build, test or run as shipped. This fixes every finding, then adds a Cloud Run track so the demo costs about £1/month idle instead of ~£150. CI (red on its first run) - api: setuptools could not build the package (flat layout with app/ and alembic/) - web: missing @types/node; `vitest run` exited 1 with no test files - pipeline: the stub run needed a gitignored VCF, and no process had a stub block - ruff pinned, mypy configured, DB tests on real Postgres (pgserver locally, service in CI) ML serving (scores were meaningless) - the registered model now carries its own feature engineering and returns predict_proba, so serving sends raw columns and cannot drift from training - resolve by registry alias (stages are deprecated in MLflow 3) and record the real version; re-scoring upserts instead of failing on the unique constraint - ClinVar labels parsed from VEP's lowercase terms Pipeline - exact ref/alt recovered from a CHROM_POS_REF_ALT VCF ID; loading is idempotent - job status reaches running/failed/succeeded, so the UI stops polling dead jobs - DATABASE_URL travels in the environment or a Nextflow secret, never on a command line - VEP cache and plugins staged as inputs; the gcp profile runs tasks on Google Batch Deployment - the API serves /api (matching the ingress); the web app reads its API URL at runtime - migrations run in an init container under a Postgres advisory lock - terraform: custom VPC shared with Batch, private Cloud SQL, API enablement, Workload Identity bindings, Secret Manager, deletion protection - serverless track, now the default: Cloud Run services scaling to zero, a Cloud Run job for the Nextflow driver, and Neon or Cloud SQL behind one DATABASE_URL secret. GKE and Argo remain, behind -var deploy_kubernetes=true. See docs/cloud.md. Correctness and security - 409 on duplicate sample names, 422 on bad paging, natural chromosome ordering, wider VEP text columns, enum dropped on downgrade, the sample's assembly actually used - vcf_uri restricted to gs:// objects or files under the data root, blocking option injection - CORS restricted to configured origins; `make down` no longer deletes volumes Data - docs/data.md records the peer-reviewed, openly licensed sources (GIAB HG002, ClinVar, gnomAD) with citations and an honest evaluation plan; `make data` fetches a chr22 slice Verified: api 50 tests, ml 18, loader 16, web 12; ruff, mypy, svelte-check, terraform validate and both kustomize overlays clean.
52 lines
1.8 KiB
Python
52 lines
1.8 KiB
Python
import pytest
|
|
from httpx import AsyncClient
|
|
from pydantic import ValidationError
|
|
|
|
from app.schemas import SampleCreate
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"uri",
|
|
[
|
|
"gs://bucket/dir/sample.vcf.gz",
|
|
"gs://my.bucket-1/a/b.bcf",
|
|
"gs://bucket/x.vcf",
|
|
"/data/example.vcf.gz",
|
|
"/data/giab/hg002.chr22.vcf.bgz",
|
|
],
|
|
)
|
|
def test_vcf_uri_accepts_gcs_objects_and_files_under_the_data_root(uri: str) -> None:
|
|
assert SampleCreate(name="s", vcf_uri=uri).vcf_uri == uri
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"uri",
|
|
[
|
|
"-c/tmp/evil.config", # would be parsed as a Nextflow option
|
|
"--outdir=/etc",
|
|
"/etc/passwd", # outside the data root
|
|
"/data/../etc/shadow.vcf", # traversal out of it
|
|
"data/example.vcf.gz", # relative: depends on the API's working directory
|
|
"gs://bucket/notes.txt", # not a VCF/BCF
|
|
"https://example.com/x.vcf.gz",
|
|
"gs:///x.vcf.gz",
|
|
"/data/x.vcf.gz\n--foo", # control characters
|
|
"",
|
|
],
|
|
)
|
|
def test_vcf_uri_rejects_everything_else(uri: str) -> None:
|
|
with pytest.raises(ValidationError):
|
|
SampleCreate(name="s", vcf_uri=uri)
|
|
|
|
|
|
async def test_bad_vcf_uri_is_422_at_the_api(client: AsyncClient) -> None:
|
|
r = await client.post("/api/samples", json={"name": "s", "vcf_uri": "/etc/passwd"})
|
|
assert r.status_code == 422
|
|
|
|
|
|
async def test_cors_allows_only_configured_origins(client: AsyncClient) -> None:
|
|
allowed = await client.get("/health", headers={"Origin": "http://localhost:5173"})
|
|
assert allowed.headers.get("access-control-allow-origin") == "http://localhost:5173"
|
|
other = await client.get("/health", headers={"Origin": "https://evil.example"})
|
|
assert "access-control-allow-origin" not in other.headers
|